Wolfram | Stephen Wolfram Readings: What’s Really Going On in Machine Learning? Some Minimal Models @WolframResearch | Uploaded August 2024 | Updated October 2024, 1 hour ago.
Stephen reads a recent blog from writings.stephenwolfram.com and then answers questions live from his viewers.
Read the blog along with Stephen: writings.stephenwolfram.com/2024/08/whats-really-going-on-in-machine-learning-some-minimal-models
Originally livestreamed at: twitch.tv/stephen_wolfram
00:00 Start stream
4:58 SW starts talking
5:49 The Mystery of Machine Learning
10:27 Traditional Neural Nets
18:12 Simplifying the Topology: Mesh Neural Nets
22:24 Making Everything Discrete: A Biological Evolution Analog
26:49 Machine Learning in Discrete Rule Arrays
43:52 Multiway Mutation Graphs
46:34 Optimizing the Learning Process
1:04:13 What Can Be Learned?
1:16:56 Other Kinds of Models and Setups
1:34:27 So in the End, What's Really Going On in Machine Learning?
1:45:32 Historical & Personal Notes
1:52:55 Q&A
2:22:32 End stream
Follow us on our official social media channels.
X: twitter.com/WolframResearch
Facebook: facebook.com/wolframresearch
Instagram: instagram.com/wolframresearch
LinkedIn: linkedin.com/company/wolfram-research
Stephen Wolfram's Twitter: twitter.com/stephen_wolfram
Contribute to the official Wolfram Community: community.wolfram.com
Stay up-to-date on the latest interest at Wolfram Research through our blog: blog.wolfram.com
Follow Stephen Wolfram's life, interests, and what makes him tick on his blog: writings.stephenwolfram.com
Stephen reads a recent blog from writings.stephenwolfram.com and then answers questions live from his viewers.
Read the blog along with Stephen: writings.stephenwolfram.com/2024/08/whats-really-going-on-in-machine-learning-some-minimal-models
Originally livestreamed at: twitch.tv/stephen_wolfram
00:00 Start stream
4:58 SW starts talking
5:49 The Mystery of Machine Learning
10:27 Traditional Neural Nets
18:12 Simplifying the Topology: Mesh Neural Nets
22:24 Making Everything Discrete: A Biological Evolution Analog
26:49 Machine Learning in Discrete Rule Arrays
43:52 Multiway Mutation Graphs
46:34 Optimizing the Learning Process
1:04:13 What Can Be Learned?
1:16:56 Other Kinds of Models and Setups
1:34:27 So in the End, What's Really Going On in Machine Learning?
1:45:32 Historical & Personal Notes
1:52:55 Q&A
2:22:32 End stream
Follow us on our official social media channels.
X: twitter.com/WolframResearch
Facebook: facebook.com/wolframresearch
Instagram: instagram.com/wolframresearch
LinkedIn: linkedin.com/company/wolfram-research
Stephen Wolfram's Twitter: twitter.com/stephen_wolfram
Contribute to the official Wolfram Community: community.wolfram.com
Stay up-to-date on the latest interest at Wolfram Research through our blog: blog.wolfram.com
Follow Stephen Wolfram's life, interests, and what makes him tick on his blog: writings.stephenwolfram.com
![Science & Technology Q&A for Kids (and others) [Part 143]](https://i.ytimg.com/vi/7Uqo_kKEztg/hqdefault.jpg "Science & Technology Q&A for Kids (and others) [Part 143]
Stephen Wolfram hosts a live and unscripted Ask Me Anything about science and technology for all ages. Find the playlist of Q&As here: https://wolfr.am/youtube-sw-qa
Originally livestreamed at: https://twitch.tv/stephen_wolfram
If you missed the original livestream of this episode, feel free to submit a question you would like Stephen to answer in a future Q&A livestream here: https://wolfr.am/12cczmv5J
00:00 Start stream
1:12: SW starts talking
1:21-17:17 Can you explain eclipse prediction like Im in middle school? High school? College?
17:31-20:17 Is it possible to view an Eclipse from space? Do astronauts on the space station see anything during eclipses?
20:22-24:10 Related to the eclipse, it is interesting that the Moon always shows the same side to Earth. Why is that? (Ive heard about commensurate frequencies, but Im not sure about the origin of this fact.)
24:11-28:53 How are orbits in the solar system so stable over time?
28:58-31:54 I wonder if it would have any effect if the Moon did rotate with respect to the Earth?
31:59-34:07 If the Moon were spinning fast, it would probably still have a liquid core, I think?
34:15-41:49 If the Moon were to be broken apart, leading to a debris field impacting Earth, what models exist to predict the scale of these impacts and their potential effects on global climate, ecosystems and people?
42:01-43:01 Is predicting eclipses harder than predicting the motions of planets or comets?
43:08-1:05:58 Can LLMs do math?
1:06:02-1:07:14 When will the AIs start colonizing space?
1:07:27-1:11:28 When we have large models of all sorts of other stuff, will LLMs primary role not actually be as the interpreters between humans and our tools?
1:11:29-1:12:48 Cant we look into the brain to find out what types of transformers or even other things we need in LLMs?
1:13:21 End stream
Follow us on our official social media channels.
X: https://twitter.com/WolframResearch/
Facebook: https://www.facebook.com/wolframresearch/
Instagram: https://www.instagram.com/wolframresearch/
LinkedIn: https://www.linkedin.com/company/wolfram-research/
Stephen Wolframs Twitter: https://twitter.com/stephen_wolfram/
Contribute to the official Wolfram Community: https://community.wolfram.com/
Stay up-to-date on the latest interest at Wolfram Research through our blog: https://blog.wolfram.com/
Follow Stephen Wolframs life, interests, and what makes him tick on his blog: https://writings.stephenwolfram.com/")
![Live CEOing Ep 818: Language Design in Wolfram Language [Failsafe, Equal-bracket Styling, and More]](https://i.ytimg.com/vi/7jF1v2ccKmY/hqdefault.jpg "Live CEOing Ep 818: Language Design in Wolfram Language [Failsafe, Equal-bracket Styling, and More]
In this episode of Live CEOing, Stephen Wolfram discusses upcoming improvements and functionality to Wolfram Language. If youd like to contribute to the discussion in future episodes, you can participate through this YouTube channel or through the official Twitch channel of Stephen Wolfram here: https://www.twitch.tv/stephen_wolfram
Follow us on our official social media channels.
Twitter: https://twitter.com/WolframResearch
Facebook: https://www.facebook.com/wolframresearch
Instagram: https://www.instagram.com/wolframresearch/
LinkedIn: https://www.linkedin.com/company/wolfram-research/
Contribute to the official Wolfram Community: https://community.wolfram.com
Stay up-to-date on the latest interest at Wolfram Research through our blog: https://blog.wolfram.com
Follow Stephen Wolframs life, interests, and what makes him tick on his blog: https://writings.stephenwolfram.com/")
![Live CEOing Ep 828: Language Design in Wolfram Language [Color From Expression and More]](https://i.ytimg.com/vi/8depTNY_jvQ/hqdefault.jpg "Live CEOing Ep 828: Language Design in Wolfram Language [Color From Expression and More]
In this episode of Live CEOing, Stephen Wolfram discusses upcoming improvements and functionality to Wolfram Language. If youd like to contribute to the discussion in future episodes, you can participate through this YouTube channel or through the official Twitch channel of Stephen Wolfram here: https://www.twitch.tv/stephen_wolfram
Follow us on our official social media channels.
Twitter: https://twitter.com/WolframResearch
Facebook: https://www.facebook.com/wolframresearch
Instagram: https://www.instagram.com/wolframresearch/
LinkedIn: https://www.linkedin.com/company/wolfram-research/
Contribute to the official Wolfram Community: https://community.wolfram.com
Stay up-to-date on the latest interest at Wolfram Research through our blog: https://blog.wolfram.com
Follow Stephen Wolframs life, interests, and what makes him tick on his blog: https://writings.stephenwolfram.com/")
